Skip to content

Commit 409f252

Browse files
committed
remove emojis
1 parent d0f4559 commit 409f252

File tree

2 files changed

+85
-0
lines changed

2 files changed

+85
-0
lines changed

java-strings/pom.xml

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -52,6 +52,13 @@
5252
<artifactId>icu4j</artifactId>
5353
<version>${icu4j.version}</version>
5454
</dependency>
55+
56+
<dependency>
57+
<groupId>com.vdurmont</groupId>
58+
<artifactId>emoji-java</artifactId>
59+
<version>4.0.0</version>
60+
</dependency>
61+
5562
</dependencies>
5663

5764
<build>
Lines changed: 78 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,78 @@
1+
package com.baeldung.string;
2+
3+
import static org.hamcrest.CoreMatchers.containsString;
4+
import static org.hamcrest.CoreMatchers.not;
5+
import static org.junit.Assert.assertThat;
6+
7+
import java.util.regex.Matcher;
8+
import java.util.regex.Pattern;
9+
10+
import org.junit.Test;
11+
12+
import com.vdurmont.emoji.EmojiParser;
13+
14+
public class RemovingEmojiFromStringUnitTest {
15+
String text = "la conférence, commencera à 10 heures 😅 ✿";
16+
String regex = "[^\\p{L}\\p{N}\\p{P}\\p{Z}]";
17+
18+
@Test
19+
public void whenRemoveEmojiUsingLibrary_thenSuccess() {
20+
String result = EmojiParser.removeAllEmojis(text);
21+
System.out.println(result);
22+
assertThat(result, not(containsString("😅")));
23+
assertThat(result, containsString("à"));
24+
assertThat(result, containsString("la"));
25+
assertThat(result, containsString("10"));
26+
}
27+
28+
@Test
29+
public void whenReplaceEmojiUsingLibrary_thenSuccess() {
30+
String result = EmojiParser.parseToAliases(text);
31+
System.out.println(result);
32+
assertThat(result, not(containsString("😅")));
33+
assertThat(result, containsString("sweat_smile"));
34+
}
35+
36+
@Test
37+
public void whenRemoveEmojiUsingRegex_thenSuccess() {
38+
String result = text.replaceAll(regex, "");
39+
System.out.println(result);
40+
assertThat(result, not(containsString("😅")));
41+
assertThat(result, containsString("à"));
42+
assertThat(result, containsString("la"));
43+
assertThat(result, containsString("10"));
44+
}
45+
46+
@Test
47+
public void whenRemoveEmojiUsingMatcher_thenSuccess() {
48+
Pattern pattern = Pattern.compile(regex, Pattern.UNICODE_CHARACTER_CLASS);
49+
Matcher matcher = pattern.matcher(text);
50+
51+
String result = matcher.replaceAll("");
52+
System.out.println(result);
53+
assertThat(result, not(containsString("😅")));
54+
assertThat(result, containsString("à"));
55+
assertThat(result, containsString("la"));
56+
assertThat(result, containsString("10"));
57+
}
58+
59+
@Test
60+
public void whenRemoveEmojiUsingCodepoints_thenSuccess() {
61+
String result = text.replaceAll("[\\x{0001f300}-\\x{0001f64f}]|[\\x{0001f680}-\\x{0001f6ff}]", "");
62+
System.out.println(result);
63+
assertThat(result, not(containsString("😅")));
64+
assertThat(result, containsString("à"));
65+
assertThat(result, containsString("la"));
66+
assertThat(result, containsString("10"));
67+
}
68+
69+
@Test
70+
public void whenRemoveEmojiUsingUnicode_thenSuccess() {
71+
String result = text.replaceAll("[\ud83c\udf00-\ud83d\ude4f]|[\ud83d\ude80-\ud83d\udeff]", "");
72+
System.out.println(result);
73+
assertThat(result, not(containsString("😅")));
74+
assertThat(result, containsString("à"));
75+
assertThat(result, containsString("la"));
76+
assertThat(result, containsString("10"));
77+
}
78+
}

0 commit comments

Comments
 (0)